mentalhealth_2016_df = read_csv("./data/mental_health_in_tech_2016.csv")
## Warning: Duplicated column names deduplicated: 'Why or why not?' => 'Why or
## why not?_1' [40]
## Parsed with column specification:
## cols(
## .default = col_character(),
## `Are you self-employed?` = col_integer(),
## `Is your employer primarily a tech company/organization?` = col_integer(),
## `Is your primary role within your company related to tech/IT?` = col_integer(),
## `Do you have medical coverage (private insurance or state-provided) which includes treatment of mental health issues?` = col_integer(),
## `Do you have previous employers?` = col_integer(),
## `Have you ever sought treatment for a mental health issue from a mental health professional?` = col_integer(),
## `What is your age?` = col_integer()
## )
## See spec(...) for full column specifications.
colnames(mentalhealth_2016_df) <- c("self_employed", "num_employees", "tech_company", "tech_role", "benefits", "care_options", "employer_discussion", "employer_help", "enonymity", "medical_leave", "mental_health_consequences", "phys_health_consequences", "coworkers_discussion", "supervisor_discussion", "mental_vs_physical", "obs_consequence", "medical_coverage", "help_resourcces", "whether_reveal_business_contacts", "reveal_concequences_business_contects", "whether_reveal_coworkers", "reveal_concequences_coworkers", "productivity_affect", "work_time_affected", "preemployers", "preemployers_benefits", "preemployers_care_options", "preemployers_discussion", "preemployer_help", "pre_anonymity", "pre_mental_health_consequences", "pre_phys_health_consequences", "pre_coworkers_discussion", "pre_supervisors_discussion", "pre_mental_vs_physical", "pre_obs_consequence", "physical_health_interview", "physical_health_interview_reason", "mental_health_interview", "mental_health_interview_reason", "career_influence", "coworkers_view", "friends_family_share", "unsupportive_badly_handled", "less_likely_reveal", "family_history", "mental_health_previous", "mental_health_now", "condition_diagnosed", "possible_condition", "professional_diagnosed", "condition_professional_diagnosed", "seek_treatment", "work_interferes_treated", "work_interferes_untreated", "age", "gender", "country_live", "territory_live", "country_work", "territory_work", "work_position_kind", "work_remotely")
percent <- function(x, digits = 2, format = "f", ...) {
paste0(formatC(100 * x, format = format, digits = digits, ...), "%")
}
data_territory = mentalhealth_2016_df %>%
select(mental_health_now, territory_work) %>%
group_by(territory_work) %>%
count(mental_health_now) %>%
spread(key = mental_health_now, value = n) %>%
janitor::clean_names() %>%
replace_na(list(maybe = 0, no = 0, yes = 0)) %>%
mutate(total = yes + no + maybe)
state_geo = read_csv("./data/statelatlong.csv") %>%
janitor::clean_names()
## Parsed with column specification:
## cols(
## State = col_character(),
## Latitude = col_double(),
## Longitude = col_double(),
## City = col_character()
## )
data_map = merge(data_territory, state_geo, by.x = "territory_work", by.y = "city") %>%
mutate(yes_percentage = percent(yes/total))
g <- list(
scope = 'usa',
projection = list(type = 'albers usa'),
showland = TRUE,
landcolor = toRGB("gray85"),
subunitwidth = 1,
countrywidth = 1,
subunitcolor = toRGB("white"),
countrycolor = toRGB("white")
)
plot_geo(data_map, locationmode = 'USA-states', sizes = c(1, 250)) %>%
add_markers(
x = ~longitude, y = ~latitude, size = ~total, color = ~territory_work, hoverinfo = "text",
text = ~str_c("Yes:",data_map$yes_percentage, "\nState:",data_map$territory_work )
) %>%
layout(title = '2016 US mental health survey<br>(Click legend to toggle)', geo = g)
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors